The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the Classification of Residual Tumor After Resection for the Forthcoming (Ninth) Edition of the TNM Classification of Lung Cancer.

INTRODUCTION: The goal of surgical resection is to completely remove a cancer; it is useful to have a system to describe how well this was accomplished. This is captured by the residual tumor (R) classification, which is separate from the TNM classification that describes the anatomic extent of a cancer independent of treatment. The traditional R-classification designates as R0 a complete resection, as R1 a macroscopically complete resection but with microscopic tumor at the surgical margin, and as R2 a resection that leaves gross tumor behind. For lung cancer, an additional category encompasses situations in which the presence of residual tumor is uncertain. METHODS: This paper represents a comprehensive review of evidence regarding these R categories and the descriptors thereof, focusing on studies published after the year 2000 and with adjustment for potential confounders. RESULTS: Consistent discrimination between complete, uncertain, and incomplete resection is revealed with respect to overall survival. Evidence regarding specific descriptors is generally somewhat limited and only partially consistent; nevertheless, the data suggest retaining all descriptors but with clarifications to address ambiguities. CONCLUSION: On the basis of this review, the R-classification for the ninth edition of stage classification of lung cancer is proposed to retain the same overall framework and descriptors, with more precise definitions of descriptors. These refinements should facilitate application and further research.

Thymic Imaging Pitfalls and Strategies for Optimized Diagnosis.

Thymic imaging is challenging because the imaging appearance of a variety of benign and malignant thymic conditions are similar. CT is the most commonly used modality for mediastinal imaging, while MRI and fluorine 18 fluorodeoxyglucose (FDG) PET/CT are helpful when they are tailored to the correct indication. Each of these imaging modalities has limitations and technical pitfalls that may lead to an incorrect diagnosis and mismanagement. CT may not be sufficient for the characterization of cystic thymic processes and differentiation between thymic hyperplasia and thymic tumors. MRI can be used to overcome these limitations but is subject to other potential pitfalls such as an equivocal decrease in signal intensity at chemical shift imaging, size limitations, unusual signal intensity for cysts, subtraction artifacts, pseudonodularity on T2-weighted MR images, early imaging misinterpretation, flow and spatial resolution issues hampering assessment of local invasion, and the overlap of apparent diffusion coefficients between malignant and benign thymic entities. FDG PET/CT is not routinely indicated due to some overlap in FDG uptake between thymomas and benign thymic processes. However, it is useful for staging and follow-up of aggressive tumors (eg, thymic carcinoma), particularly for detection of occult metastatic disease. Pitfalls in imaging after treatment of thymic malignancies relate to technical challenges such as postthymectomy sternotomy streak metal artifacts, differentiation of postsurgical thymic bed changes from tumor recurrence, or human error with typical "blind spots" for identification of metastatic disease. Understanding these pitfalls enables appropriate selection of imaging modalities, improves diagnostic accuracy, and guides patient treatment. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the TNM Stage Groups in the Forthcoming (Ninth) Edition of the TNM Classification for Lung Cancer.

INTRODUCTION: The TNM classification of lung cancer is periodically revised. The International Association for the Study of Lung Cancer collected and analyzed a new database to inform the forthcoming ninth edition of the TNM classification. The results are herewith presented. METHODS: After exclusions, 76,518 patients from a total of 124,581 registered patients were available for analyses: 58,193 with clinical stage, 39,192 with pathologic stage, and 62,611 with best stage NSCLC. The proposed new N2 subcategories (N2a, involvement of single ipsilateral mediastinal or subcarinal nodal station, and N2b, involvement of multiple ipsilateral mediastinal nodal stations with or without involvement of the subcarinal nodal station) and the new M1c subcategories (M1c1, multiple extrathoracic metastases in one organ system, and M1c2, multiple extrathoracic metastases in multiple organ systems) were considered in the survival analyses. Several potential stage groupings were evaluated, using multiple analyses, including recursive partitioning, assessment of homogeneity within and discrimination between potential groups, clinical and statistical significance of survival differences, multivariable regression, and broad assessment of generalizability. RESULTS: T1N1, T1N2a, and T3N2a subgroups are assigned to IIA, IIB, and IIIA stage groups, respectively. T2aN2b and T2bN2b subgroups are assigned to IIIB. M1c1 and M1c2 remain in stage group IVB. Analyses reveal consistent ordering, discrimination of prognosis, and broad generalizability of the proposed ninth edition stage classification of lung cancer. CONCLUSIONS: The proposed stages for the ninth edition TNM improve the granularity of nomenclature about anatomic extent that has benefits as treatment approaches become increasingly differentiated and complex.

International reproducibility study of thymic epithelial tumors staging: pT stage is an issue. proposals for improvement. A RYTHMIC/ITMIG study.

INTRODUCTION: Pathologists are staging thymic epithelial tumors (TET) according to the 8th UICC/AJCC TNM system. Within the French RYTHMIC network, dedicated to TET, agreement on pathologic tumor stage (pT) among the pathology panelists was difficult. The aim of our study was to determine the interobserver reproducibility of pT at an international level, to explore the source of discrepancies and potential interventions to address these. METHODS: An international panel of pathologists was recruited through the International Thymic Malignancy Interest Group (ITMIG). The study focused on invasion of mediastinal pleura, pericardium, and lung. From a cohort of cases identified as challenging within the RYTHMIC network, we chose a series of test and validation cases (n = 5 and 10, respectively). RESULTS: Reproducibility of the pT stage was also challenging at an international level as none of the 15 cases was classified as the same pT stage by all ITMIG pathologists. The agreement rose from slight (κ = 0.13) to moderate (κ = 0.48) between test and validation series. Discussion among the expert pathologists pinpointed two major reasons underlying discrepancies: 1) Thymomas growing with their "capsule" and adhering to the pleurae, pericardium, or lung were often misinterpreted as invading these structures. 2) Recognition of the mediastinal pleura was identified as challenging. CONCLUSION: Our study underlines that the evaluation of the pT stage of TET is problematic and needs to be addressed in more detail in an upcoming TNM classification. The publication of histopathologic images of landmarks, including ancillary tests could improve reproducibility for future TNM classifications.

The International Association for the Study of Lung Cancer Staging Project for Lung Cancer: Proposals for the Revision of the M Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Lung Cancer.

INTRODUCTION: This study analyzed all metastatic categories of the current TNM classification of NSCLC to propose modifications of the M component in the next edition (ninth) of the classification. METHODS: A database of 124,581 patients diagnosed between 2011 and 2019 was established; of these, 14,937 with NSCLC in stages IVA to IVB were available for this analysis. Overall survival was calculated using the Kaplan-Meier method, and prognosis was assessed using multivariable-adjusted Cox proportional hazards regression. RESULTS: The eighth edition M categories revealed good discrimination in the ninth edition data set. Assessments revealed that an increasing number of metastatic lesions were associated with decreasing prognosis; because this seems to be a continuum and adjustment for confounders was not possible, no specific lesion number was deemed appropriate for stage classification. Among tumors involving multiple metastases, decreasing prognosis was found with an increasing number of organ systems involved. Multiple assessments, including after adjustment for potential confounders, revealed that M1c patients who had metastases to a single extrathoracic organ system were prognostically distinct from M1c patients who had involvement of multiple extrathoracic organ systems. CONCLUSIONS: These data validate the eighth edition M1a and M1b categories, which are recommended to be maintained. We propose the M1c category be divided into M1c1 (involvement of a single extrathoracic organ system) and M1c2 (involvement of multiple extrathoracic organ systems).

Backlogs in formal interpretation of radiology examinations: a pilot global survey.

OBJECTIVE: Anecdotal reports from imaging facilities globally suggest growing radiology interpretation reporting delays. This pilot study's primary aim was to estimate the backlog of formal interpretation of imaging examinations. METHODS: An online survey was distributed to radiologists globally to gather practice-specific characteristics, imaging volumes, and reporting for 3 types of examinations (brain/head CT scans, chest CT scans, and chest radiographs) at 4 time points: 7, 30, 90 days, and 6 months. RESULTS: We received responses from 49 radiologists in 16 countries on six continents. Unreported examinations (backlog) were present in thirty of 44 (68%) facilities. Backlogs for brain/head CT, chest CT, and chest radiographs were present in, respectively, 48%, 50%, and 59% of facilities at 7 days and 20%, 23%, and 32% of facilities at 6 months. When present, the mean proportion of backlog (range) at 7 days was 17% (1 to 96) for brain/head CT, 18% (3 to 82) for chest CT, and 22% (1 to 99) for chest radiographs. CONCLUSIONS: Our findings from this pilot study show a widespread global backlog in reporting common imaging examinations, and further research is needed on the issue and contributing factors.

Postoperative Radiation Therapy for Thymic Carcinoma: An Analysis of the International Thymic Malignancy Interest Group/European Society of Thoracic Surgeons Database.

INTRODUCTION: R0 resection and radiation therapy have been associated with improved overall survival (OS) in patients with thymic carcinoma (TC). Here, we analyzed which subgroups of patients derive the greatest benefit from postoperative radiation therapy (PORT). METHODS: Clinical, pathologic, treatment, and survival information of 462 patients with TC from the International Thymic Malignancy Interest Group/European Society of Thoracic Surgeons database were analyzed. Variables included age, sex, continent of treatment, paraneoplastic syndrome, carcinoma subtype, tumor size, pathologic Masaoka stage, resection status, and use of chemotherapy. OS was the primary end point using the Kaplan-Meier method. Time to recurrence (TTR) was the secondary end point using a competing risk analysis. A 3-month landmark analysis was performed. RESULTS: PORT was associated with a significant OS benefit (5-y OS 68% versus 53%, p = 0.002). In patients with R0 resection, PORT was associated with increased OS for advanced (stages III-IV, p = 0.04), but not early (stages I-II, p = 0.14) stage TC. In patients with an R1/2 resection of advanced-stage TC, PORT was associated with significantly longer OS (5-y OS 53% versus 38%; p < 0.001). Subset analyses did not reveal clear associations of PORT with TTR. On multivariable analysis, lower pathologic stage, PORT, and R0 resection status were associated with an OS benefit, whereas only higher age and lower pathologic stage had an association with longer TTR. CONCLUSIONS: In the largest individual patient data set on patients with TC reported to date, PORT was associated with a meaningful OS benefit in patients with advanced-stage TC after an R0 or R1/2 resection.

The International Association for the Study of Lung Cancer Thymic Epithelial Tumors Staging Project: Proposals for the N and the M Components for the Forthcoming (Ninth) Edition of the TNM Classification of Malignant Tumors.

INTRODUCTION: Stage classification is an important underpinning of management in patients with cancer and rests on a combination of three components-T for tumor extent, N for nodal involvement, and M for distant metastases. This article details the revision of the N and the M components of thymic epithelial tumors for the ninth edition of the TNM classification of malignant tumors proposed by the Thymic Domain of the International Association for the Study of Lung Cancer Staging and Prognostic Factors Committee. METHODS: The N and M components of the eighth edition staging system were verified by a large international collaborative data source through a data-driven analysis. A total of 9147 cases were included for analysis, including 7662 thymomas, 1345 thymic carcinomas, and 140 neuroendocrine thymic tumors. RESULTS: Lymph node involvement rates were 1.5% in thymomas and 17.6% and 27.7% in thymic carcinomas and neuroendocrine thymic tumors, respectively. Rates of lymph node metastasis were increasingly higher in tumors with higher T stage and higher-grade histologic type. Survival analysis validated the differences in the N and M categories proposed in the eighth edition staging system. Good discrimination in overall survival was detected among pathologic (p)N and pM categories in patients with thymoma and thymic carcinoma. CONCLUSIONS: No changes are proposed from the eighth edition for the N and M components. The proposed stage classification will provide a useful tool for management of the disease among the global thymic community.

Retrospectively assessing evaluation and management of artificial-intelligence detected nodules on uninterpreted chest radiographs in the era of radiologists shortage.

PURPOSE: High volumes of chest radiographs (CXR) remain uninterpreted due to severe shortage of radiologists. These CXRs may be informally reported by non-radiologist physicians, or not reviewed at all. Artificial intelligence (AI) software can aid lung nodule detection. Our aim was to assess evaluation and management by non-radiologists of uninterpreted CXRs with AI detected nodules, compared to retrospective radiology reports. MATERIALS AND METHODS: AI detected nodules on uninterpreted CXRs of adults, performed 30/6/2022-31/1/2023, were evaluated. Excluded were patients with known active malignancy and duplicate CXRs of the same patient. The electronic medical records (EMR) were reviewed, and the clinicians' notes on the CXR and AI detected nodule were documented. Dedicated thoracic radiologists retrospectively interpreted all CXRs, and similarly to the clinicians, they had access to the AI findings, prior imaging and EMR. The radiologists' interpretation served as the ground truth, and determined if the AI-detected nodule was a true lung nodule and if further workup was required. RESULTS: A total of 683 patients met the inclusion criteria. The clinicians commented on 386 (56.5%) CXRs, identified true nodules on 113 CXRs (16.5%), incorrectly mentioned 31 (4.5%) false nodules as real nodules, and did not mention the AI detected nodule on 242 (35%) CXRs, of which 68 (10%) patients were retrospectively referred for further workup by the radiologist. For 297 patients (43.5%) there were no comments regarding the CXR in the EMR. Of these, 77 nodules (11.3%) were retrospectively referred for further workup by the radiologist. CONCLUSION: AI software for lung nodule detection may be insufficient without a formal radiology report, and may lead to over diagnosis or misdiagnosis of nodules.

The International Association for the Study of Lung Cancer Staging Project for Lung Cancer: Proposals for the Revision of the N Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Lung Cancer.

INTRODUCTION: The accurate assessment of nodal (N) status is crucial to the management and prognostication of nonmetastatic NSCLC. We sought to determine whether the current N descriptors should be maintained or revised for the upcoming ninth edition of the international TNM lung cancer staging system. METHODS: Data were assembled by the International Association for the Study of Lung Cancer on patients with NSCLC, detailing both clinical and pathologic N status, with information about anatomical location and individual station-level identification. Survival was calculated by the Kaplan-Meier method and prognostic groups were assessed by a Cox regression analysis. RESULTS: Data for clinical N and pathologic N status were available in 45,032 and 35,009 patients, respectively. The current N0 to N3 descriptors for both clinical N and pathologic N categories reflect prognostically distinct groups. Furthermore, single-station N2 involvement (N2a) exhibited a better prognosis than multistation N2 involvement (N2b) in both clinical and pathologic classifications, and the differences between all neighboring nodal subcategories were highly significant. The prognostic differences between N2a and N2b were robust and consistent across resection status, histologic type, T category, and geographic region. CONCLUSIONS: The current N descriptors should be maintained, with the addition of new subdescriptors to N2 for single-station involvement (N2a) and multiple-station involvement (N2b).

Persistent Severe Acute Respiratory Syndrome Coronavirus 2 Pneumonia in Patients Treated With Anti-CD20 Monoclonal Antibodies.

We report 8 cases of persistent severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pneumonia in patients previously treated with anti-CD20 monoclonal antibodies. Polymerase chain reaction of nasopharyngeal swabs for SARS-CoV-2 was negative in most cases; viral cell cultures confirmed that viable SARS-Co-2 virus was present. Four patients were treated with anti-SARS-CoV-2 hyperimmune globulins with rapid resolution of disease.

The International Association for the Study of Lung Cancer Thymic Epithelial Tumor Staging Project: A Re-Assessment of the International Thymic Malignancy Interest Group/International Association for the Study of Lung Cancer Lymph Node Map for Thymic Epithelial Tumors for the Forthcoming Ninth Edition of the TNM Classification of Malignant Tumors.

INTRODUCTION: A lymph node map is the pillar on which accurate assignment and documentation of nodal classification stands. The International Thymic Malignancy Interest Group created the first map for thymic epithelial malignancies in conjunction with the eighth edition of the TNM classification, representing the first official TNM classification of thymic epithelial malignancies. The map was based on clinical experience and published studies, but it was largely empirical because of limited available data. Dissemination of the map and implementation of a standard thymic stage classification across the world in 2017 have provided more consistent and granular data. METHODS: More than twice as many cases of node involvement are available for analysis in the current database compared with that of the eighth edition database, allowing validation of many aspects of the eighth edition map. This article details the process and considerations for refinement of the thymic map for the ninth TNM used by the Thymic Domain of the Staging and Prognostic Factors Committee of the International Association for the Study of Lung Cancer. The committee evaluated a large international collaborative data set, published anatomical and clinical studies pertaining to lymph node spread from thymic epithelial tumors, in conjunction with the analysis underlying refinements of the TNM components for the ninth edition TNM classification. RESULTS: The node map boundaries of the N1 and N2 categories remain unchanged. Visual clarifications have been added to the nomenclature of nodal stations within these regions. CONCLUSIONS: On the basis of the recommendation to keep the N component unchanged for the ninth edition TNM classification, the lymph node map remains unchanged as well; however, clarifications have been added to facilitate clinical use.

The International Association for the Study of Lung Cancer Thymic Epithelial Tumors Staging Project: Proposal for a Stage Classification for the Forthcoming (Ninth) Edition of the TNM Classification of Malignant Tumors.

INTRODUCTION: A TNM-based system for all types of thymic epithelial tumors was introduced in the eighth edition of the TNM classification of thoracic malignancies. The Thymic Domain of the Staging and Prognostic Factors Committee of the International Association for the Study of Lung Cancer, composed of multispecialty international experts, was charged to develop proposals for the ninth edition. This article outlines the proposed definitions for the T, the N, and the M components and their combination into stage groups. METHODS: A large central database of 11,347 patients with thymic epithelial tumors was assembled thanks to the contribution of the major thymic organizations worldwide and analyses were carried out for the T, the N, and the M components and the stage groups. Overall survival was the outcome measure for patients with completely and incompletely resected tumors, and recurrence for those with complete resection. When the number of patients was sufficient, analyses were performed separately for thymomas, thymic carcinomas, and neuroendocrine thymic tumors. RESULTS: Tumor size is included in the T1 category as T1a (≤5cm) and T1b (>5 cm); the mediastinal pleura is dropped as a T descriptor; invasion of the lung or phrenic nerve is reclassified as T2 (instead of T3). No changes are proposed for the N and the M components from the eighth edition. The stage groups remain the same. CONCLUSIONS: The proposed changes for the ninth edition of the TNM classification set the stage for further progress in the future for these rare tumors.

Imaging evaluation of thymic tumors.

An integral part of managing patients with thymoma and thymic carcinoma is imaging. At diagnosis and staging, imaging helps demonstrate the extent of local invasion and distant metastases which allows the proper stratification of patients for therapy. For decades, the predominant staging system for thymic tumors was the Masaoka-Koga staging system. More recently, however, the International Association for the Study of Lung Cancer, the International Thymic Malignancies Interest Group (ITMIG), the European Society of Thoracic Surgeons, the Chinese Alliance for Research on Thymomas, and the Japanese Association of Research on Thymus partnered together to develop a tumor-node-metastasis (TNM) staging system specifically for thymic tumors based on a retrospective database of nearly 10,000 patients. The TNM 8th edition defines specific criteria for thymic tumors. Imaging also serves to assess treatment response and detect recurrent disease after various treatment modalities. The Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 is currently used to assess response to treatment. ITMIG recommends certain modifications to RECIST version 1.1, however, in thymic tumors due to unique patterns of spread. While there is often overlap, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography/computed tomography (PET/CT) characteristics can help differentiate thymoma and thymic carcinoma, with newer CT and MRI techniques under evaluation showing encouraging potential.

The International Association for the Study of Lung Cancer Thymic Epithelial Tumors Staging Project: An Overview of the Central Database Informing Revision of the Forthcoming (Ninth) Edition of the TNM Classification of Malignant Tumors.

INTRODUCTION: In 2014, a TNM-based system for thymic epithelial tumors was proposed. The TNM stage classification system was published as a result of a joint project from the International Association for the Study of Lung Cancer and the International Thymic Malignancy Interest Group for the eighth edition of the American Joint Commission on Cancer and the Union for International Cancer Control stage classification system. The Thymic Domain of the Staging and Prognostic Factors Committee of the International Association for the Study of Lung Cancer received the mandate to make proposals for the ninth edition of the TNM stage classification. METHODS: A central thymic database was collected by the Cancer Research And Biostatistics with the contribution of the major thymic associations in the world. RESULTS: A total of 11,347 patients were collected. Submitting organizations were the following: Japanese Association for Research in the Thymus, European Society of Thoracic Surgeons, Chinese Alliance for Research in Thymoma, Korean Association for Research in the Thymus, International Thymic Malignancy Interest Group, and Réseau tumeurs THYMiques et Cancer. Additional contributions came from centers in the United States, United Kingdom, Turkey, Australia, Spain, and Italy. A total of 9147 cases were eligible for analysis. Eligible cases for analysis came from Asia and Australia (5628 cases, 61.5%), Europe (3113 cases, 34.0%), and North America (406 cases, 4.4%). CONCLUSIONS: This report provides an overview of the database that has informed the proposals for the updated T, N, and M components and the stage groups for the ninth TNM of malignant tumors.

Effects of EGFR driver mutations on pathologic regression in resectable locally advanced non-small cell lung cancer treated with neoadjuvant chemoradiation and completion surgery.

OBJECTIVE: We hypothesized that driver mutations in epidermal growth factor receptor (EGFR) are associated with decreased pathologic response to neoadjuvant chemoradiation (NA-ChRT) in locally advanced non-small cell lung cancer (LA-NSCLC). METHODS: Patients with Stage IIB-IIIA NSCLC treated with NA-ChRT, completion surgery, and underwent molecular profile testing were identified in a lung cancer database. Pathologic response was quantified using: (i) major pathologic response (MPR), (ii) complete pathologic response (pCR), and (iii) mean residual viable tumor cells (MRTC). Two groups were formed based on the presence or absence of driver mutations. Clinical and pathological correlations between the groups were studied. RESULTS: Forty-seven patients underwent tumor molecular profile testing, NA-ChRT, and completion surgery. Compared to the no-driver mutation group, the driver mutation group had lower MPR (23% vs 71%, p = 0.003), pCR (0% vs 26%, p = 0.02), and higher MRTC (43.4% vs 15.8%, p = 0.009). Univariate analysis showed an increased MPR rate for smokers, squamous cell histology, ChRT-surgery interval >65 days, and no-driver mutations. Multivariate analysis showed that only no-driver mutations (OR 0.39, p = 0.02) remained significant for MPR. PD-L1 status did not affect MPR. At 2 years, the driver mutation group had lower rates of local control (Hazard ration [HR] 0.67, p = 0.17) and disease-free survival (HR 0.5, p = 0.001). Overall survival was similar for both groups (HR = 1.04, p = 0.86). CONCLUSION: Following 60 Gray NA-ChRT, tumors with a driver mutation had lower MPR and pCR rates than tumors without a driver mutation. PD-L1 was not associated with tumor regression. ADVANCES IN KNOWLEDGE: Patients with resectable LA-NSCLC and an EGFR driver mutation treated with neoadjuvant-ChRT and completion surgery have reduced pathologic regression, lower local control rates, and shorter disease-free survival than patients without a driver mutation. Evaluation of molecular testing should be introduced in LA-NSCLC intended for prognostication and treatment decisions.

The International Association for the Study of Lung Cancer Thymic Epithelial Tumor Staging Project: Proposal for the T Component for the Forthcoming (Ninth) Edition of the TNM Classification of Malignant Tumors.

INTRODUCTION: A TNM-based stage classification system of thymic epithelial tumors was adopted for the eighth edition of the stage classification of malignant tumors. The Thymic Domain of the Staging and Prognostics Factor Committee of the International Association for the Study of Lung Cancer developed a new database with the purpose to make proposals for the ninth edition stage classification system. This article outlines the proposed definitions for the T categories for the ninth edition TNM stage classification of thymic malignancies. METHODS: A worldwide collective database of 11,347 patients with thymic epithelial tumors was assembled. Analysis was performed on 9147 patients with available survival data. Overall survival, freedom-from-recurrence, and cumulative incidence of recurrence were used as outcome measures. Analysis was performed separately for thymomas, thymic carcinomas, and neuroendocrine thymic tumors. RESULTS: Proposals for the T categories include the following: T1 category is divided into T1a (≤5 cm) and T1b (>5 cm), irrespective of mediastinal pleura invasion; T2 includes direct invasion of the pericardium, lung, or phrenic nerve; T3 denotes direct invasion of the brachiocephalic vein, superior vena cava, chest wall, or extrapericardial pulmonary arteries and veins; and T4 category remains the same as in the eighth edition classification, involving direct invasion of the aorta and arch vessels, intrapericardial pulmonary arteries and veins, myocardium, trachea, or esophagus. CONCLUSIONS: The proposed T categories for the ninth edition of the TNM classification provide good discrimination in outcome for the T component of the TNM-based stage system of thymic epithelial tumors.

Magnetic resonance imaging for prospective assessment of local recurrence of non-small cell lung cancer after stereotactic body radiation therapy.

OBJECTIVES: To evaluate multi-parametric MRI for distinguishing stereotactic body radiation therapy (SBRT) induced pulmonary fibrosis from local recurrence (LR). MATERIALS AND METHODS: SBRT treated non-small cell lung cancer (NSCLC) patients suspected of LR by conventional imaging underwent MRI: T2 weighted, diffusion weighted imaging, dynamic contrast enhancement (DCE) with a 5-minute delayed sequence. MRI was reported as high or low suspicion of LR. Follow-up imaging ≥12 months or biopsy defined LR status as proven LR, no-LR or not-verified. RESULTS: MRI was performed between 10/2017 and 12/2021, at a median interval of 22.5 (interquartile range 10.5-32.75) months after SBRT. Of the 20 lesions in 18 patients: 4 had proven LR, 10 did not have LR and 6 were not verified for LR due to subsequent additional local and/or systemic therapy. MRI correctly identified as high suspicion LR in all proven LR lesions and low suspicion LR in all confirmed no-LR lesions. All proven LR lesions (4/4) showed heterogeneous enhancement and heterogeneous T2 signal, as compared to the proven no-LR lesions in which 7/10 had homogeneous enhancement and homogeneous T2 signal. DCE kinetic curves could not predict LR status. Although lower apparent diffusion coefficient (ADC) values were seen in proven LR lesions, no absolute cut-off ADC value could determine LR status. CONCLUSION: In this pilot study of NSCLC patients after SBRT, multi-parametric chest MRI was able to correctly determine LR status, with no single parameter being diagnostic by itself. Further studies are warranted.

Multimodal fusion models for pulmonary embolism mortality prediction.

Pulmonary embolism (PE) is a common, life threatening cardiovascular emergency. Risk stratification is one of the core principles of acute PE management and determines the choice of diagnostic and therapeutic strategies. In routine clinical practice, clinicians rely on the patient's electronic health record (EHR) to provide a context for their medical imaging interpretation. Most deep learning models for radiology applications only consider pixel-value information without the clinical context. Only a few integrate both clinical and imaging data. In this work, we develop and compare multimodal fusion models that can utilize multimodal data by combining both volumetric pixel data and clinical patient data for automatic risk stratification of PE. Our best performing model is an intermediate fusion model that incorporates both bilinear attention and TabNet, and can be trained in an end-to-end manner. The results show that multimodality boosts performance by up to 14% with an area under the curve (AUC) of 0.96 for assessing PE severity, with a sensitivity of 90% and specificity of 94%, thus pointing to the value of using multimodal data to automatically assess PE severity.